specific method · filed under post-training
Domain-Specialized RL Experts
A setup that trains a separate expert for each broad domain and reasoning-effort level rather than a separate RL model for every task.
Also called scaling RL across three broad domains.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 1
Documented in
Evidence
1 span quoted from the sources, strongest treatment first.
Rather than training specialized RL models for individual tasks, we scale RL across three broad domains, each encompassing a wide spectrum of sub-tasks, and train a single expert for each domain at every reasoning effort level
usedunclearin Kimi K3Moonshot AI
Filed alongside
Other methods under post-training :: reinforcement learning algorithm.
Group Relative Policy OptimizationReinforcement LearningGroupwise Advantage RedistributionFreezing the MoE Router During Reinforcement LearningIcePopOff-Policy Sequence MaskingReinforcement Learning from Verifiable RewardsRollout Routing ReplayUnbiased KL EstimateAsynchronous Group Relative Policy OptimizationChain-of-Thought Reinforcement LearningDirect Double-Sided Importance SamplingKeep Sampling MaskMixed Reinforcement LearningPivot Reinforcement LearningReinforcement Learning Post-TrainingAbstention TrainingAdvantage ShapingAgentic RL Task MixCISPO with Length-Weighted Leave-One-Out Group-Relative AdvantagesConcatenated Routing ReplayDerived-Latency PenaltyDomain-Specific GRPO TrainingDropping All-Zero-Advantage Groups